Accurately predicting the temperature field of turbine blades is of great significance for evaluating the thermal reliability and service life of high-temperature components in aero-engines. However, due to the high computational cost of numerical simulations and the limitations imposed by complex geometric structures and harsh operating environments, experimental measurements can usually only obtain sparse sensor data, making the acquisition of complete temperature distributions still challenging. Therefore, reconstructing the complete temperature field under sparse measurement conditions has become a key research issue in turbine thermal analysis. To address this problem, this paper proposes an attention-enhanced CNN–LSTM framework for reconstructing transient turbine blade temperature fields from sparse data. The model combines the spatial feature extraction capability of Convolutional Neural Networks (CNNs) with the time-series modeling capability of Long Short-Term Memory networks (LSTM). An SE channel attention module is introduced in the CNN feature extraction stage to achieve adaptive recalibration of channel features, and a temporal attention mechanism is incorporated after the LSTM layer to highlight key transient thermal features. A multi-condition temperature field dataset was constructed by conducting Computational Fluid Dynamics (CFD) simulations on low-pressure turbine guide vanes, and the model was experimentally validated through thermal shock tests. The results show that the proposed model can accurately reconstruct the spatial distribution and transient evolution of the turbine blade temperature field under sparse measurement conditions. Under different operating conditions, the predicted temperature fields are highly consistent with the CFD results, with the maximum Reconstruction error remaining below 19 °C. Error distribution analysis indicates that the model has stable Reconstruction performance and good generalization ability.
Chen et al. (2026) studied this question.